Inverse-and-Edit: Simple and Effective Framework for Fast Image Editing
cs.CV
Submitted: 2025-06-23
Updated: 2026-10-28
Comments: The project page with visual results is available at iliabeletskii.github.io/inverse-and-edit
Code: https://github.com/ControlGenAI/Inverse-and-Edit
License: http://creativecommons.org/licenses/by/4.0/
The gist: Diffusion-based text-to-image models have recently been distilled into few-step samplers and fast generators, reducing inference cost while maintaining high image quality.
Terminology
Abstract
Diffusion-based text-to-image models have recently been distilled into few-step samplers and fast generators, reducing inference cost while maintaining high image quality. However, text-guided editing with such accelerated backbones remains challenging: inversion in a small number of steps is unreliable, local errors accumulate along the trajectory, and existing fast-editing methods typically rely on backbone-specific inversion procedures, which limits their transferability. In this work, we propose a simple and universal framework for text-guided image editing with arbitrary accelerated diffusion and flow-matching models. Instead of optimizing local, per-timestep objectives, we directly minimize a global editing objective over the entire inversion-generation trajectory. The framework fine-tunes only 1.5-7 % of the base-model parameters through two lightweight LoRA adapters (forward and backward), trained on fewer than 10 K triplets from the publicly available HQ-Edit dataset. We validate our method on three architecturally distinct backbones: consistency-distilled SD1.5 LCM-Dreamshaper, adversarial-distilled SDXL-Turbo, and rectified-flow-distilled Z-Image-Turbo. On PIE-Bench, our method achieves the strongest editing alignment within each backbone family while ensuring a strong level of content preservation. Inference adds no extra steps beyond the standard inversion and editing passes. The project page with visual results is available at iliabeletskii.github.io/inverse-and-edit.
Sources
- Universal Guidance for Diffusion Models
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
- Multistep Consistency Models
- Prompt-to-Prompt Image Editing with Cross Attention Control
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning
- Denoising Diffusion Probabilistic Models
- Microsoft COCO: Common Objects in Context
- DINOv2: Learning Robust Visual Features without Supervision
- Progressive Distillation for Fast Sampling of Diffusion Models
- Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
- Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Consistency Models
- Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
- PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
- Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
- Inversion-Free Image Editing with Natural Language
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs